Department of Computer Science

Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/16

Browse

Subject: search.filters.subject.FA17

Search Results

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    DressUp (Sentiment Analysis of Product Reviews)
    (Library Information Services, COMSATS University Islamabad, Lahore Campus., 2021-11-20) Maaz Hussain; SP17-BSE-096; Sobia Usman; LHR TP 7136
    E-commerce is process of doing business through computer. A person can buy anything using computer. With increase in this business it enables everyone to sell their items on internet, so there are a lot of items on ecommerce sites with good and bad ratings and it is difficult for customer to find the best one. The aim of this project is to develop a clothing portal which helps customers to buy genuine and best rated products. By using machine learning approach, we have performed sentimental analysis of products rating and review (comments) and generate rating to fulfil customer satisfaction against products. We divide positive and negative rating so user can distinguish which product is better. Sentiment analysis uses NLP and text analysis (opinion mining) technique to identify rating from text. Many new companies perform sentiment analysis to understand the sentiments of people for their products to perform business analysis and increase sale.
  • No Thumbnail Available
    Item
    TradeUp.biz - Business Management Information System V5.0
    (Library Information Services, COMSATS University Islamabad, Lahore Campus., 2021-11-20) Suleman Tariq; FA17-BSE-006; Asif Shahzad; LHR TP 7059
    TradeUp.biz is a web-based business management information system to manage small to medium scale businesses like single/multi-branch shops, warehouses and distribution agencies. This system facilitates the basic work flow like development, deployment and maintenance easy. Basic features related to products, sales, stock and purchase management are done by former students, we aim to refine and optimize existing features in addition to developing new features and modules required by such business to operate more optimized way. Our aim is to add a Progressive Web App based e-commerce feature, improvement of existing features, implementing Redux for state management in complete application, multibranch business management and many more.
  • No Thumbnail Available
    Item
    VSLDR (Vehicle Security and Drowsiness Recognition)
    (Library Information Services, COMSATS University Islamabad, Lahore Campus., 2021-11-20) Zubair Ahmad; FA17-BCS-106; Momina Shaheen
    A vehicle is generally the most costly and significant resource close to a home, so this framework empowers you to keep this advantage readily available by utilizing remote innovation. Consider it a remote rope to your vehicle. In today’s world vehicles form a significant asset to us, without which our life would be divided. Concerning the security of our vehicles, we are incredibly helpless. It is of an inconceivable concern, particularly in metropolitan urban areas, where these occurrences happen each day. So, we have zeroed in on the security of vehicles and drowsiness identification. As of late, the misfortunes of vehicle crashes achieved by driving vehicles have been consistently expanding. In particular, there are more serious wounds and passing than minor injuries, and the mischief as a result of huge disasters is growing. In particular, generous cargo trucks and quick vehicle accidents that occur during driving at the night have created authentic social issues. The arrangement comprises a blend of software and hardware. This entire framework will permit you to associate with your vehicle whenever, anyplace, and confirm its security.
  • No Thumbnail Available
    Item
    Physio AID
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Kazim Haider (FA17- BCS-114), Abdul Raffay (FA17- BCS-150), Hamna Ashraf (FA17- BCS-140); LHR TP 8025; Sara Muneeb
    Going to the Doctor after a bone fracture surgery is always a nuisance, you’re given a set of exercises to perform for a stipulated period of time. Then you’ll go back to the doctor to see signs of any potential progress. But what if there is no progress? What if you learn that you’ve been doing the exercises all wrong and now, you’ll have to start all over? Such incidents are very common with physiotherapy patients and they not only waste time and effort but can also be painful. In an effort to rid ourselves from this issue, we’ve deduced a scheme of allowing technology to take over and once again make our lives easier. A physiotherapy app that gives real-time feedback regarding the patient’s exercise routine, his form and the duration of the exercise will help make our life a lot easier. Making this vision into a reality will help save costs from a weekly or monthly visit to the doctor as well as streamlining the entire post-surgery experience
  • No Thumbnail Available
    Item
    Client APIs are Effected by Web APIs Evolution
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Farrukh Liaquat; FA17-RCS-002; LHR TP 7281; Dr. Ghulam Rasool
    Web APIs (Application Programming Interfaces) evolution means updating the APIs to improve their performance. Web services are used for communication between applications such as Facebook, Youtube, etc. The commonly used protocols in web services are SOAP (Simple Object Access Protocol), REST (Representational State Transfer), JSON (JavaScript Object Notation), WPS (Web Processing Service), WSCL (Web Services Conversation Language), WSFL (Web Services Flow Language) and XML-RPC (XML Remote Procedure Call). The SOAP is with strict rules and allows only XML data format while REST is a Representational State Transfer and it allows a combination of different messaging data formats such as HTML, JSON, XML, and plain text. The APIs versioning consists of some changes such as adding new methods and parameters, updating methods and parameters names, and deleting methods and parameters. These changes provide an opportunity to analyze design patterns and antipatterns. The APIs may have incomplete functionalities, which shows immature APIs updates. The APIs updates bring new and improved functionalities as well as incompatibilities and integration problems for client developers. The client developers have to modify their client programs according to these changes to use new APIs. However, much prior work is found related to web services (web APIs), but our research work is mainly related to client APIs as well as web APIs. The main objective of this research is to analyze web APIs evolution pains as well as pain-causing factors to client APIs. For this purpose, we use the versioning history approach, and record the changelog of web APIs such as Youtube, and performed empirical analysis. We invoke web APIs for the detection of antipatterns. We develop a reverse engineering Add-in in Sparx System for reverse engineering of the web APIs. The Add-in automatically generates source code metrics from source code dll. The Add-in extracts 9 artifacts from source code such as the number of interfaces, number of classes, number of fields, number of code files, number of namespaces, disk size, manifest, and availability. We extract source code metrics from 10 web APIs such as Alchemy, BestBuy, Bitly, Dropbox, External-IP, Facebook, Instagram, TeamViewer, WhatsApp, and YouTube. We also extract source code metrics from 10 open-source client projects APIs such as NewtonSoft, RestSharp, NLog, SharpZipLib, Protobuf-net, Zxing, Telegram, Lucene, SharpDX, and AForge. We perform empirical analysis on source code metrics and analyzed that the APIs evolve due to Changing the number of interfaces, Changing the number of classes, Changing the number x of methods, Changing the number of fields, Changing the number of code files, Changing the number of namespaces, and Changing the size of the file. When web APIs evolve, client APIs also evolve respectively to accommodate these changes. Therefore, client APIs are effected by web APIs evolution
  • No Thumbnail Available
    Item
    An Empirical Study of Urdu Noun and Verb Phrase Chunking
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Maryam Khurshid; FA17-RCS-025; LHR TP 5979; Dr. Muhammad Waqas Anwar
    Urdu is a language which is a morphologically rich and weak resourced language. The distinguishing features such as free word order, context-sensitive orthography, flexible grammar rules and complex morphology makes the representation of the Urdu language a difficult problem area. In Urdu's hand-written text the words are written without any space among them. A computer needs a text file that needs a separator when a word ends with a non-joiner character. Without these separators, the words will join with one another that will not be understandable for language native speakers. Chunking is a basic technique used for entity detection that labels and segments the sequence of Multi tokens. Chunking technique helps in the progress of many Natural Processing Applications. Chunking is a mature field while dealing with other languages like Hindi, English, Chinese and Turkish but it still requires the attention of researchers in the Urdu language. The Native speakers of Urdu language are more than 70 Million. The study is about the noun and verb phrase chunking in the Urdu language. The intention of this work is to explore the corpus accuracy based on the Noun and verb phrase chunking of the Urdu language. Chunking is an NLP (natural language processing) function that focuses on splitting a text into syntactically linked non-overlapping and non-exhaustive word-groups i.e. a word could only be a part of one chunk but not all words are in chunks. Different experiments are conducted on this work by using a tag set of different input and output schemes with the same Methodology. Firstly, the corpus is selected then preprocessing is performed on that corpus. After that part of speech tagging and IOB tags are assigned to that corpus then Noun and verb phrases are detected by neural networks and machine learning techniques. After this Noun and Verb phrases are detected from a corpus. At last, evaluation will be done by using different Parameters like F-call, recall and Precision.
  • No Thumbnail Available
    Item
    Detecting Urdu Semantic Textual Similarity through Word and Sentence Embedding Techniques
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2019) Muhammad Farhat Ullah; FA17-RCS-019; LHR TP 5625; Dr. Rao Muhammad Adeel Nawab
    Semantic Textual Similarity (STS) evaluates the degree to which two sentences or short texts are semantically proportional to one another. STS is one of the significant prob lems in the field of Natural Language Processing (NLP). Text reuse and plagiarism detection are famous examples of STS. STS has three types; (1) Monolingual STS: if the source and suspicious short texts are in the same language. (2) Multilingual STS: if the source is in one language and sus picious short text is more than two languages. (3) Cross-lingual STS: if the source in one language and suspect is in the other language, often translation of each other. STS could be found several levels, for example, word, sentence, paragraph, and document level. Urdu is one of the low resource languages. It’s the National Language of Pakistan, also widely spoken and used in electronic, print media of Pakistan, India, and Bangladesh. The main aim of this thesis is to develop techniques that measure STS as paragraph level for the Urdu language. Our thesis aims to develop and investigate the new feature extraction techniques to ad dress the problem of STS for Urdu. We divide it into three layers, (1) Train Word and Sentence Embedding models on Urdu datasets, (2) Apply these new feature extraction techniques to extract feature from Urdu short text pairs, and (3) Apply machine learn ing classification algorithms for Urdu STS. In the first step we train Word and Sentence Embedding models on Urdu datasets. By using these embedding models, we extract the word, and sentence embedding features from pre-processed Urdu Short Text Reuse Corpus (USTRC) short texts. After that, we find the cosine similarity between these extracted feature vectors, then apply classification algorithms on similarity to classify short texts into verbatim, paraphrased and independently written. In word embedding techniques, we used Word2Vec, GloVe, and FastText with Addition, Average, and Mul tiplication Functions also we explored Smooth Inverse (SI) and Term Frequency (TF) weighted word embedding techniques. In sentence embedding techniques we have used two unsupervised (sent2vec and LASER) and two supervised (InferSent and BERT) ix techniques. We have used seven machine learning algorithms to classify similarity score including, Naive Bayes (NB), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbour (KNN), Gradient Boost (GB), Multi-Layer Percep tron (MLP). To evaluate these classifiers, we apply F1 measure. We got best F1 measure = 0.68, 0.75, 0.92, 0.70 by using sent2vec sentence embedding technique with GB and MLP classifiers.